---
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: base_korean_audio_cls
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# base_korean_audio_cls

This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4289
- Accuracy: 0.9160

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.6381        | 1.0   | 30   | 2.6167          | 0.1429   |
| 2.3354        | 2.0   | 60   | 2.1583          | 0.3950   |
| 1.575         | 3.0   | 90   | 1.6064          | 0.6387   |
| 1.1257        | 4.0   | 120  | 1.2644          | 0.7479   |
| 0.6466        | 5.0   | 150  | 0.8699          | 0.8487   |
| 0.3732        | 6.0   | 180  | 0.6579          | 0.8235   |
| 0.2168        | 7.0   | 210  | 0.5271          | 0.8655   |
| 0.1484        | 8.0   | 240  | 0.4143          | 0.9160   |
| 0.1208        | 9.0   | 270  | 0.4386          | 0.9160   |
| 0.1074        | 10.0  | 300  | 0.4289          | 0.9160   |


### Framework versions

- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0